Buddy and Mosaic were roughly even in both shared sandbox benchmarks.
Median of each benchmark's primary metric; lower is better. Medians within 5% count as roughly even, and a benchmark gets no speed verdict when either provider completed fewer than 50% of runs.
Time from sandbox creation to the first successful command, with 100 sandboxes launched at the same time.
Time to interactive
The medians are within 5% of each other (905ms vs 889ms), so this counts as roughly even.
6 runs from October 2, 2026 to October 30, 2026.
A real developer workload: install system packages, download Bun, clone the opencode repo, then run bun install and bun typecheck.
Total workload time
The medians are within 5% of each other (59.09s vs 58.64s), so this counts as roughly even.
4 runs from October 16, 2026 to October 30, 2026.
Have another question? Email us.
Buddy and Mosaic were roughly even in both shared sandbox benchmarks. In Burst TTI (October 30, 2026), Buddy had a median time to interactive of 905ms and Mosaic 889ms, which counts as roughly even. In DAX (October 30, 2026), Buddy had a median total workload time of 59.09s and Mosaic 58.64s, which counts as roughly even.